<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhangxiaoyi-etal-2025-ccl25">
    <titleInfo>
        <title>CCL25-Eval任务4系统报告:基于叙实性分类和语境特征的大语言模型叙实性推理</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zhangxiaoyi</namePart>
        <namePart type="family">Zhangxiaoyi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">鲁嘉琪</namePart>
        <namePart type="family">鲁嘉琪</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhang</namePart>
        <namePart type="family">Da</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoyu</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">卢达威</namePart>
        <namePart type="family">卢达威</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hongfei</namePart>
            <namePart type="family">Lin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bin</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hongye</namePart>
            <namePart type="family">Tan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Chinese Information Processing Society of China</publisher>
            <place>
                <placeTerm type="text">Jinan, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>“叙实性推理是机器理解文本隐含事实的关键能力之一,核心在于结合动词的语义判断动词宾语命题的真值。本研究基于首届中文叙实性推理评测任务4(FIE2025)开展叙实性推理研究,经过前期对不同模型的测验和比对,选择了Deepseek-R1模型为基座模型。提示语的总体撰写思路是:首先将动词叙实性进行分类,从传统的三分法扩展至五分法(叙实、弱叙实、反叙实、非叙实、半叙实),同时,对自然语料与人造语料进行差异化处理,再针对部分语义复杂的动词编写更加细致的判断规则。最终结果显示,自然语料的正确率达到0.9155,人造语料的正确率为0.9541,总正确率达到0.9261。”</abstract>
    <identifier type="citekey">zhangxiaoyi-etal-2025-ccl25</identifier>
    <location>
        <url>https://aclanthology.org/2025.ccl-2.11/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>96</start>
            <end>104</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CCL25-Eval任务4系统报告:基于叙实性分类和语境特征的大语言模型叙实性推理
%A Zhangxiaoyi, Zhangxiaoyi
%A 鲁嘉琪, 鲁嘉琪
%A Da, Zhang
%A Chen, Xiaoyu
%A 卢达威, 卢达威
%Y Lin, Hongfei
%Y Li, Bin
%Y Tan, Hongye
%S Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025)
%D 2025
%8 August
%I Chinese Information Processing Society of China
%C Jinan, China
%F zhangxiaoyi-etal-2025-ccl25
%X “叙实性推理是机器理解文本隐含事实的关键能力之一,核心在于结合动词的语义判断动词宾语命题的真值。本研究基于首届中文叙实性推理评测任务4(FIE2025)开展叙实性推理研究,经过前期对不同模型的测验和比对,选择了Deepseek-R1模型为基座模型。提示语的总体撰写思路是:首先将动词叙实性进行分类,从传统的三分法扩展至五分法(叙实、弱叙实、反叙实、非叙实、半叙实),同时,对自然语料与人造语料进行差异化处理,再针对部分语义复杂的动词编写更加细致的判断规则。最终结果显示,自然语料的正确率达到0.9155,人造语料的正确率为0.9541,总正确率达到0.9261。”
%U https://aclanthology.org/2025.ccl-2.11/
%P 96-104

Markdown (Informal)

[CCL25-Eval任务4系统报告:基于叙实性分类和语境特征的大语言模型叙实性推理](https://aclanthology.org/2025.ccl-2.11/) (Zhangxiaoyi et al., CCL 2025)

• CCL25-Eval任务4系统报告:基于叙实性分类和语境特征的大语言模型叙实性推理 (Zhangxiaoyi et al., CCL 2025)

ACL

• Zhangxiaoyi Zhangxiaoyi, 鲁嘉琪 鲁嘉琪, Zhang Da, Xiaoyu Chen, and 卢达威 卢达威. 2025. CCL25-Eval任务4系统报告:基于叙实性分类和语境特征的大语言模型叙实性推理. In Proceedings of the 24th China National Conference on Computational Linguistics (CCL 2025), pages 96–104, Jinan, China. Chinese Information Processing Society of China.